INVESTIGADORES
STEGMAYER Georgina Silvia
congresos y reuniones científicas
Título:
Comparison of a Radial Neural Network model with a Genetic Algorithm for estimating the Particle Size Distribution of a Latex
Autor/es:
G. STEGMAYER, L. CLEMENTI, J. VEGA
Lugar:
Santa Fe
Reunión:
Conferencia; Conferencia Latinoamericana de Informática (CLEI2008); 2008
Institución organizadora:
CLEI
Resumen:
This paper presents the comparison of an Artificial NeuralNetwork (ANN)-based model and a Genetic Algorithm (GA) as independenttools for estimating the particle size distribution (PSD) of a polymerlatex, which is an important physical characteristic that determines someend-use properties of the material. The PSD of a dilute latex is estimatedfrom dynamic light scattering (DLS) measurements, taken at several angles.To this effect, an ANN-based model and GAs are used as a toolfor solving the involved ill-conditioned inverse problem. Both models aretrained with a large set of measurements simulated from typical asymmetricPSDs, represented by unimodal and bimodal normal-logarithmicdistributions of variable geometric mean diameters and variances. Theproposed approaches are evaluated on the basis of both simulated andexperimental examples.
